Proceedings of the 4th Symposium on Information and Communication Technology最新文献_第4页

Principal direction analysis-based real-time 3D human pose reconstruction from a single depth image 基于主方向分析的单幅深度图像实时三维人体姿态重建

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542071

Dong-Luong Dinh, Hee-Sok Han, H. J. Jeon, Sungyoung Lee, Tae-Seong Kim

{"title":"Principal direction analysis-based real-time 3D human pose reconstruction from a single depth image","authors":"Dong-Luong Dinh, Hee-Sok Han, H. J. Jeon, Sungyoung Lee, Tae-Seong Kim","doi":"10.1145/2542050.2542071","DOIUrl":"https://doi.org/10.1145/2542050.2542071","url":null,"abstract":"Human pose estimation in real-time is a challenging problem in computer vision. In this paper, we present a novel approach to recover a 3D human pose in real-time from a single depth human silhouette using Principal Direction Analysis (PDA) on each recognized body part. In our work, the human body parts are first recognized from a depth human body silhouette via the trained Random Forests (RFs). On each recognized body part which is presented as a set of 3D points cloud, PDA is applied to estimate the principal direction of the body part. Finally, a 3D human pose gets recovered by mapping the principal directional vector to each body part of a 3D human body model which is created with a set of super-quadrics linked by the kinematic chains. In our experiments, we have performed quantitative and qualitative evaluations of the proposed 3D human pose reconstruction methodology. Our evaluation results show that the proposed approach performs reliably on a sequence of unconstrained poses and achieves an average reconstruction error of 7.46 degree in a few key joint angles. Our 3D pose recovery methodology should be applicable to many areas such as human computer interactions and human activity recognition.","PeriodicalId":246033,"journal":{"name":"Proceedings of the 4th Symposium on Information and Communication Technology","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124369620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Document classification using semi-supervived mixture model of von Mises-Fisher distributions on document manifold 文献流形上von Mises-Fisher分布半监督混合模型的文献分类

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542066

N. K. Anh, Ngo Van Linh, L. Ky, Tam The Nguyen

引用次数: 2

Mobile peer-to-peer approach for social computing services in distributed environment 分布式环境下的移动点对点社会计算服务

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542064

Ha Manh Tran, K. V. Huynh, K. D. Vo, Son Thanh Le

{"title":"Mobile peer-to-peer approach for social computing services in distributed environment","authors":"Ha Manh Tran, K. V. Huynh, K. D. Vo, Son Thanh Le","doi":"10.1145/2542050.2542064","DOIUrl":"https://doi.org/10.1145/2542050.2542064","url":null,"abstract":"This paper presents a mobile peer-to-peer approach that can be applied to build social computing services in distributed environment. This approach features peer-to-peer networks with the support of mobile devices that allows users to participate in social computing services including data sharing and searching services. Due to the limitations of system resource and network connectivity, mobile peers cannot easily undertake complicated operations, such as processing complex queries, indexing and transmitting large amount of data. This approach employs a super peer peer-to-peer network to deal with the problem of peer heterogeneity. It uses workstations as peers to assist mobile peers with insufficient storage, bandwidth and processing capability in dealing with complicated operations, while mobile peers possess ordinary operations such as publishing and searching data. We have extended the Gnutella protocol to provide operations on peers and mobile peers. The evaluation of the prototyping system has performed on a number of laboratory workstations and Android emulators to investigate the feasibility and scalability of the system.","PeriodicalId":246033,"journal":{"name":"Proceedings of the 4th Symposium on Information and Communication Technology","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123268818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Modeling and debugging numerical constraints of cyber-physical systems design 网络物理系统设计的数值约束建模与调试

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542068

T. N. Tien, S. Nakajima, H. Thang

引用次数: 6

Violent scene detection using mid-level feature 使用中级特征的暴力场景检测

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542070

Vu Lam, Sang Phan Le, T. Ngo, Duy-Dinh Le, D. Duong, S. Satoh

{"title":"Violent scene detection using mid-level feature","authors":"Vu Lam, Sang Phan Le, T. Ngo, Duy-Dinh Le, D. Duong, S. Satoh","doi":"10.1145/2542050.2542070","DOIUrl":"https://doi.org/10.1145/2542050.2542070","url":null,"abstract":"Violent scene detection (VSD) refers to the task of detecting shots containing violent scenes in videos. With a wide range of promising real-world applications (e.g. movies/films inspection, video on demand, semantic video indexing and retrieval), VSD has been an important research problem. A typical approach for VSD is to learn a violent scene classifier and then apply it to video shots. Finding good feature representation for video shots is therefore essential to achieving high classification accuracy. It has been shown in recent work that using low-level features results in disappointing performance, since low-level features cannot convey high-level semantic information to represent violence concept. In this paper, we propose to use mid-level features to narrow the semantic gap between low-level features and violence concept. The mid-level features of a training (or test) video shots are formulated by concatenating scores returned by attribute classifiers. Attributes related to violence concept are manually defined. Compared to the original violence concept, the attributes have smaller gap to the low-level feature. Each corresponding attribute classifier is trained by using low-level features. We conduct experiments on MediaEval VSD benchmark dataset. The results show that, by using mid-level features, our proposed method outperforms the standard approach directly using low-level features.","PeriodicalId":246033,"journal":{"name":"Proceedings of the 4th Symposium on Information and Communication Technology","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131796339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Initializing reservoirs with exhibitory and inhibitory signals using unsupervised learning techniques 使用无监督学习技术初始化具有展示和抑制信号的储层

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542087

Sebastián Basterrech, V. Snás̃el

{"title":"Initializing reservoirs with exhibitory and inhibitory signals using unsupervised learning techniques","authors":"Sebastián Basterrech, V. Snás̃el","doi":"10.1145/2542050.2542087","DOIUrl":"https://doi.org/10.1145/2542050.2542087","url":null,"abstract":"The trend of Reservoir Computing (RC) has been gaining prominence in the Neural Computation community since the 2000s. In a RC model there are at least two well-differentiated structures. One is a recurrent part called reservoir, which expands the input data and historical information into a high-dimensional space. This projection is carried out in order to enhance the linear separability of the input data. Another part is a memory-less structure designed to be robust and fast in the learning process. RC models are an alternative of Turing Machines and Recurrent Neural Networks to model cognitive processing in the neural system. Additionally, they are interesting Machine Learning tools to Time Series Modeling and Forecasting. Recently a new RC model was introduced under the name of Echo State Queueing Networks (ESQN). In this model the reservoir is a dynamical system which arises from the Queueing Theory. The initialization of the reservoir parameters may influence the model performance. Recently, some unsupervised techniques were used to improve the performance of one specific RC method. In this paper, we apply these techniques to set the reservoir parameters of the ESQN model. In particular, we study the ESQN model initialization using Self-Organizing Maps. Additionally, we test the model performance initializing the reservoir employing Hebbian rules. We present an empirical comparison of these reservoir initializations using a range of time series benchmarks.","PeriodicalId":246033,"journal":{"name":"Proceedings of the 4th Symposium on Information and Communication Technology","volume":"238 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132118535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Time series symbolization and search for frequent patterns 时间序列符号化和频繁模式搜索

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542057

Mai Van Hoan, M. Exbrayat

引用次数: 4

In situ spatial AR surgical planning using projector-Kinect system 使用投影- kinect系统的原位空间AR手术计划

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542060

Rong Wen, Binh P. Nguyen, Chin-Boon Chng, C. Chui

{"title":"In situ spatial AR surgical planning using projector-Kinect system","authors":"Rong Wen, Binh P. Nguyen, Chin-Boon Chng, C. Chui","doi":"10.1145/2542050.2542060","DOIUrl":"https://doi.org/10.1145/2542050.2542060","url":null,"abstract":"Traditional surgical planning is challenged by limited spatial information of 2-D medical images or separated planning phases between 3-D model based virtual planning and its in situ registration. This paper presents an augmented surgical planning method with model-section views of an actual patient body and direct augmented interaction to realize spatially interactive planning in situ. A projector-Kinect system is proposed to construct a spatially augmented reality surgical environment directly on the patient body through surgical models' projection, correction and registration. Hand gesture based direct augmented interaction is developed to provide surgeons with interactive guidance during planning. The physical patient's body is augmented by the integration of medical information like 3-D anatomic and pathologic models as well as the 2-D medical images. Compared to conventional planning methods, this augmented planning enables surgical planning in 3-D space on the actual patient, and allows the planning to be integrated into an in situ robot-assisted surgical environment. Experimental results demonstrate that the method can facilitate spatial information perception and convey virtual planning on the physical patient in situ.","PeriodicalId":246033,"journal":{"name":"Proceedings of the 4th Symposium on Information and Communication Technology","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124383132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 24

Hierarchical emotion classification using genetic algorithms 基于遗传算法的分层情感分类

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542075

Ba-Vui Le, J. Bang, Sungyoung Lee

引用次数: 5

Probabilistic models for uncertain data 不确定数据的概率模型

Proceedings of the 4th Symposium on Information and Communication Technology Pub Date : 2013-12-05 DOI: 10.1145/2542050.2542051

P. Senellart

引用次数: 0